Triple

T1225252
Position Surface form Disambiguated ID Type / Status
Subject Kilmarnock E26311 entity
Predicate hasTwinTown P919 FINISHED
Object Herstal
Herstal is an industrial town in the Liège province of eastern Belgium, known historically for its arms manufacturing and proximity to the city of Liège.
 E156268 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Herstal | Statement: [Kilmarnock, hasTwinTown, Herstal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Herstal
Context triple: [Kilmarnock, hasTwinTown, Herstal]
  • A. Namur
    Namur is a historic Belgian city and the capital of Wallonia, located at the confluence of the Meuse and Sambre rivers.
  • B. Breda
    Breda is a historic city in the southern Netherlands known for its medieval architecture, former status as a military and political center, and vibrant cultural life.
  • C. Charleroi
    Charleroi is a major industrial city in the Walloon region of Belgium, historically important as a fortified stronghold and later as a center of coal mining and heavy industry.
  • D. Hasselt
    Hasselt is a historic small city in the Dutch province of Overijssel, known for its medieval center and canals.
  • E. Liège
    Liège is a major city in eastern Belgium known for its industrial heritage, vibrant cultural scene, and position along the Meuse River.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Herstal
Triple: [Kilmarnock, hasTwinTown, Herstal]
Generated description
Herstal is an industrial town in the Liège province of eastern Belgium, known historically for its arms manufacturing and proximity to the city of Liège.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Herstal
Target entity description: Herstal is an industrial town in the Liège province of eastern Belgium, known historically for its arms manufacturing and proximity to the city of Liège.
  • A. Namur
    Namur is a historic Belgian city and the capital of Wallonia, located at the confluence of the Meuse and Sambre rivers.
  • B. Breda
    Breda is a historic city in the southern Netherlands known for its medieval architecture, former status as a military and political center, and vibrant cultural life.
  • C. Charleroi
    Charleroi is a major industrial city in the Walloon region of Belgium, historically important as a fortified stronghold and later as a center of coal mining and heavy industry.
  • D. Hasselt
    Hasselt is a historic small city in the Dutch province of Overijssel, known for its medieval center and canals.
  • E. Liège
    Liège is a major city in eastern Belgium known for its industrial heritage, vibrant cultural scene, and position along the Meuse River.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69a49484688c8190a1bf285eb396a8b6 completed March 1, 2026, 7:33 p.m.
NER Named-entity recognition batch_69a4be382c4081909238c18b805352a7 completed March 1, 2026, 10:31 p.m.
NED1 Entity disambiguation (via context triple) batch_69acce5bdd248190a66551c814dcfac4 completed March 8, 2026, 1:18 a.m.
NEDg Description generation batch_69acceda83f08190b191c0c1432108b0 completed March 8, 2026, 1:20 a.m.
NED2 Entity disambiguation (via description) batch_69accfc65c008190affa13bee507bf6e completed March 8, 2026, 1:24 a.m.
Created at: March 1, 2026, 7:47 p.m.